For entities to interact meaningfully in a distributed simulation environment, coherence among the entities' states must be maintained. Because continuous state updates for all entities in the simulation normally require large amounts of network bandwidth, motion equations (i.e., dead-reckoning models) are frequently used to reduce the number of communications updates. However, even with the use of such dead-reckoning models, networking and communications limitations still exist in currently fielded systems. An effective approach to reducing the communications requirements is achieved by replacing these predictive dead-reckoning models with neural networks. This paper presents the background and motivation for the research, the architecture and training algorithms of the networks, and the integration of the networks into a large-scale simulation environment. Quantitative measures from the experiments reveal that the use of neural networks can effectively reduce the number of communication updates required to maintain entity-state coherence. However, the neural networks may also be more difficult to scale than the currently used dead-reckoning algorithms.
[1] Smith, S., and Petty, M., “Controlling autonomous behavior in real-time simulation”, In Proceedings of the Second Conference in Computer Generated Forces and Behavior Representation, Orlando FL, 1992.
2.
[2] Vargas, J.J., DeMara, R.F., Gonzalez, A.J., and Georgiopoulos, M., “Bandwidth and latency implications of integrated training and tactical communication networks,” In Proceedings of SAWMAS-04, Cocoa Beach, FL, 2004.
3.
[3] Cebula D.P., and DiCaprio, P.N., “Tradeoffs involved with separating aggregated data packets into attribute cluster packets.” In Proceedings of the 14th Workshop on Standards for the Interoperability of Distributed Simulations, Orlando FL, 1996.
4.
[4] Vargas, J.J., DeMara, R.F., Georgiopoulos, M., Gonzalez, A.J., and Marshall, H., “PDU bundling and replication for reduction of distributed simulation communication traffic,”Journal of Defense Modeling and Simulation, 1(3), (2004), 173–185.
5.
[5] Liang, L.A.H., Cai, W., Lee, B-S., and Turner, S.J., “Performance analysis of packet bundling techniques in DIS.” In Proceedings of the 3rd IEEE International Workshop on distributed interactive simulation and real-time applications, pp. 75–82, Greenbelt MD, 1999.
6.
[6] Stone, S., Zyda, M., Brutzman, D., and Falby, J., “Mobile agents and smart networks for distributed simulation.” In Proceedings of the 14th Workshop on Standards for the Interoperability of Distributed Simulations, Orlando, FL, March 1996.
7.
[7] Wuerfel, R.D., and Johnston, R., “Real-time performance of RTI version 1.3.” In Proceedings of the 1998 Fall Simulation Interoperability Workshop, September, 1998.
8.
[8] Calvin, J.O., Seeger, J., Troxel G.D., and Van Hook D.J., “STOW realtime information transfer and networking system architecture.” In Proceedings of the 12th Workshop on Standards for the Interoperability of Distributed Simulations, Orlando FL, 1995.
9.
[9] Ceranowicz, A., Torpey, M., Helfinstine, W., Evans J., and Hines, J., “Reflections on building the joint experimental federation.” In Proceedings of the 2002 I/ITSEC, Orlando FL, 2002.
10.
[10] Bassiouni, M., Chiu, M., Loper, M., Garnsey, M., and Williams, J., “Performance and reliability analysis of relevance filtering for scalable distributed interactive simulation.” In ACM Transactions on Modeling and Computer Simulation (TOMACS), volume 7, (1997), pp. 293–331.
11.
[11] Purdy S.G., and Wuerfel, R.D., “A comparison of HLA and DIS real-time performance.” In Proceedings of 1998 Spring Simulation Interoperability Workshop, Orlando FL, March 1998.
12.
[12] Wang B., and Hou, J., “Multicast routing and its QoS extension: problems, algorithms, and protocols.”IEEE Network, 14, (2000).
13.
[13] Wills, C., Mikhailov, M., and Shang, H., “N for the price of 1: Bundling Web objects for more efficient content delivery,” In Proceedings of the Tenth International Conference on World Wide Web, Hong Kong, 2001, pp. 257–265.
14.
[14] Taylor, D., “DIS-Lite & Query Protocol” In Proceedings of the 13th DIS Workshop on Standards for the Interoperability of Distributed Simulations, 1995.
15.
[15] Lin, K., and Ng, H., “Coordinate transformations in distributed interactive simulation (DIS)”, Simulation, vol. 61, No. 5, (1993), pp. 326–331.
16.
[16] Calder, R. B., Smith, J. E., Courtemanche, A. J., Mar, J. M., and Ceranowicz, A., “ModSAF behavior, simulation and control”, In Proceedings of the 3rd Conference on Computer Generated Forces and Behavioral Representation, pp. 347–356, Orlando FL, 1993.
17.
[17] Sidani T. A., and Gonzalez, A. J., “A framework for learning implicit expert knowledge through observation”,Transactions of the Society for Computer Simulation, Vol. 17, No. 2, (2000), 54–72
18.
[18] Murray-Smith R., and Johansen, T. A., Multiple Model Approaches to Modeling and Control, Taylor and Francis: UK, 1997.
19.
[19] Narendra, K. S., Balakrishnan, J., and Ciliz, K., “Adaptation and learning using multiple models, switching and tuning”,IEEE Control Systems Magazine, (1995), 37–51.
20.
[20] Brooks, R. A., “A robust layered control system for a mobile robot”,IEEE Journal of Robotics and Automation, RA-2, (1986), pp. 14–23.
21.
[21] Gallinari, P., “Modular neural net systems: training of”, In M.A., Arbib (editor), The Handbook of Brain Theory and Neural Networks, pp. 582–585, Bradford Books/MIT Press: Boston, MA, 1995.
22.
[22] Hrycej, T., Modular Learning in Neural Networks, John Wiley: Chichester, 1992.
23.
[23] Pratt, L. Y., Mostow J., and Kamm, C. A., “Direct transfer of learned information among neural networks,” In Proceedings of the Ninth National Conference on Artificial Intelligence (AAI-91), pp. 584–589, Anaheim, CA, 1991.
24.
[24] Ourston, D., Blanchard, D., Chandler E., and Loh, E., “From CIS to software,” In Proceedings of the Fifth Conference on Computer Generated Forces and Behavior Representation. Orlando, FL., May 1995, pp. 275–285.
25.
[25] Henninger A. E., and Gonzalez, A.J., “Automated acquisition tool for tactical knowledge,” In Proceedings of the 10th Annual International Florida Artificial Intelligence Research Symposium, pp. 307–311, Daytona Beach FL., 1997.
26.
[26] Hampshire J. B., and Waibel, A. H., “The Meta-PI Network: building distributed representations for robust multisource pattern recognition”,IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(7), (1992), 751–769.
27.
[27] Gonzalez, A. J., Gerber, W. J., DeMara, R. F., and Georgiopoulos, M., “Context-driven Near-term Intention Recognition”,Journal of Defense Modeling and Simulation, Volume 1, Number 3, pp. 153–170, August 2004
28.
[28] Henninger, A. E., “Neural Network Based Movement Models to Improve the Predictive Utility of Entity State Synchronization Methods for Distributed Simulations”, Doctoral Dissertation, Electrical and Computer Engineering Department, University of Central Florida, Fall, 2000.
